#Operator

4周前

OpenAI 新发布的 AI 智能体，把之前的 Operator （网页操作智能体）、Deep Research（深度研究）和 Codex （终端智能体）三合一了，并且运行在一个虚拟机中，可以灵活的组合这些子智能体共同完成任务，扬长避短！

OpenAI新德里发布会：ChatGPT语音翻译功能引发热议· 327 条信息

#OpenAI #AI智能体 #Operator #Deep Research #Codex

6个月前

这一段日子，新闻焦点全是 DeepSeek，其他重要事件就不显眼了。我说的重要事件是，1月23日，就在 DeepSeek R1 模型发布三天后，OpenAI 公司推出了一个新的 AI 工具，叫做 Operator（操作员）。我认为，这个工具可能预示着，传统互联网的最终衰落。

#DeepSeek #OpenAI #Operator

6个月前

让Operator 去抓取X Timeline 上的10条内容，Operator操作半天给我返回了几条Post的链接，短期之内可能都是用来做做demo，到真正产生生产力还有很长路要走。 1、Operator 会在云端记录你的Session，比如之前登录过再次登录就不需要密码，但这个安全性怎么保证？ 2、Operator 目前的能力还是只能完成点一点，输入文本类似的操作，更复杂的操作就无能为力了。

#Operator #X Timeline #demo #生产 #安全性 #能力 #操作

白板报 Whiteboard

6个月前

用ChatGPT Operator发推，需要经过两次确认，第一是发布的内容，第二是询问是否post，这个不能自动完成，因为事关社交媒体的发言，ChatGPT认为这是安全级别很高的操作，故需要人工审核。

#ChatGPT #Operator #推特发布 #人工审核 #安全操作

白板报 Whiteboard

6个月前

这条内容是用ChatGPT Operator自动发布的

#ChatGPT #自动发布 #人工智能 #Operator

6个月前

ChatGPT的Operator，可以用自然语言操作浏览器。通过不断往4o发截图实现，想象空间大，能完成简单操作，但目前很难用： 1. 4o不太聪明 2. 慢 3. “分辨率”低有三段视频帮你进一步理解，为防降权，链接逐条放评论： 1. Operator值不值得200美元体验？ 2. 当AI用浏览器回复微博 3. 玩井字棋

#ChatGPT #Operator #自然语言处理 #浏览器 #AI #井字棋

6个月前

继续测试 OpenAI Operator，华而不实呀！让它用 v0 dev 给我做个页面，做完了给我测试好。第一次不知道去YouTube找个真的URL帮我测试，非要编造一个，第二次出 Bug 了，点了fix按钮，但是不知道发送消息，得我手动接管，后来不知道怎么就卡死了。 Prompt：Please use v0[.]dev to build a page which can download a youtube video's thumbnail via youtube url, seo friendly. please find a sample video from youtube[.]com to verify it after you finish developing, no need to confirm anything with me, just build and test, share the project url with me when it works.

#OpenAI #Operator #v0.dev #bug #YouTube #测试

Andrej Karpathy

6个月前

Projects like OpenAI’s Operator are to the digital world as Humanoid robots are to the physical world. One general setting (monitor keyboard and mouse, or human body) that can in principle gradually perform arbitrarily general tasks, via an I/O interface originally designed for humans. In both cases, it leads to a gradually mixed autonomy world, where humans become high-level supervisors of low-level automation. A bit like a driver monitoring the Autopilot. This will happen faster in digital world than in physical world because flipping bits is somewhere around 1000X less expensive than moving atoms. Though the market size and opportunity feels a lot bigger in physical world. We actually worked on this idea in very early OpenAI (see Universe and World of Bits projects), but it was incorrectly sequenced - LLMs had to happen first. Even now I am not 100% sure if it is ready. Multimodal (images, video, audio) just barely got integrated with LLMs last 1-2 years, often bolted on as adapters. Worse, we haven’t really been to the territory of very very long task horizons. E.g. videos are a huge amount of information and I’m not sure that we can expect to just stuff it all into context windows (current paradigm) and then expect it to also work. I could imagine a breakthrough or two needed here, as an example. People on my TL are saying 2025 is the year of agents. Personally I think 2025-2035 is the decade of agents. I feel a huge amount of work across the board to make it actually work. But it *should* work. Today, Operator can find you lunch on DoorDash or check a hotel etc, sometimes and maybe. Tomorrow, you’ll spin up organizations of Operators for long-running tasks of your choice (eg running a whole company). You could be a kind of CEO monitoring 10 of them at once, maybe dropping in to the trenches sometimes to unblock something. And things will get pretty interesting.

#OpenAI #Operator #AI #Robots #Humanoid #DigitalWorld #PhysicalWorld

6个月前

A research preview of Operator, an agent that can use its own browser to perform tasks for you.

#Research #Technology #AI #automation #browser_agent #Operator